区域不变表示中的支持度和可逆性
Support and Invertibility in Domain-Invariant Representations
摘要:
学习领域不变表示已经成为无监督领域自适应的一种流行方法,并且通常通过调用一套特定的理论结果来证明。我们认为,有两个重大缺陷,在这种论点。首先,所讨论的结果仅适用于固定的表示,并且不考虑在不可逆变换中丢失的信息。其次,域不变性通常是一个过于严格的要求,并不总是导致一致的估计,即使在强大和有利的假设。在这项工作中,我们给泛化界无监督域自适应,通过承认不可逆性的成本,适用于任何表示函数。此外,我们发现,惩罚密度之间的距离往往是浪费,并提出了一个界的基础上测量的程度,支持的源域覆盖的目标域。我们在著名的基准测试上进行实验,说明了当前标准实践的不足。
英文摘要:
Learning domain-invariant representations has become a popular approach to unsupervised domain adaptation and is often justified by invoking a particular suite of theoretical results. We argue that there are two significant flaws in such arguments. First, the results in question hold only for a fixed representation and do not account for information lost in non-invertible transformations. Second, domain invariance is often a far too strict requirement and does not always lead to consistent estimation, even under strong and favorable assumptions. In this work, we give generalization bounds for unsupervised domain adaptation that hold for any representation function by acknowledging the cost of non-invertibility. In addition, we show that penalizing distance between densities is often wasteful and propose a bound based on measuring the extent to which the support of the source domain covers the target domain. We perform experiments on well-known benchmarks that illustrate the short-comings of current standard practice.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。